def main():
parser = argparse.ArgumentParser()
parser.add_argument("clinVarXmlFilename")
parser.add_argument('-a', "--assembly", default="GRCh38")
args = parser.parse_args()
printHeader()
inputBuffer = ""
with open(args.clinVarXmlFilename) as inputFile:
inClinVarSet = False
for line in inputFile:
#print "inClinVarSet", inClinVarSet, " input:", line.rstrip()
if "<ClinVarSet" in line:
inHeader = False
inputBuffer = line
inClinVarSet = True
elif "</ClinVarSet>" in line:
inputBuffer += line
inClinVarSet = False
cvs = ET.fromstring(inputBuffer)
if clinvar.isCurrent(cvs):
submissionSet = clinvar.clinVarSet(cvs)
processSubmission(submissionSet, args.assembly)
inputBuffer = None
elif inClinVarSet:
inputBuffer += line
def main():
parser = argparse.ArgumentParser()
parser.add_argument("clinVarXmlFilename")
parser.add_argument('-a', "--assembly", default="GRCh38")
args = parser.parse_args()
printHeader()
inputBuffer = ""
with open(args.clinVarXmlFilename) as inputFile:
inClinVarSet = False
for line in inputFile:
if "<ClinVarSet" in line:
inHeader = False
inputBuffer = line
inClinVarSet = True
elif "</ClinVarSet>" in line:
inputBuffer += line
inClinVarSet = False
cvs = ET.fromstring(inputBuffer)
if clinvar.isCurrent(cvs):
submissionSet = clinvar.clinVarSet(cvs)
processSubmission(submissionSet, args.assembly)
inputBuffer = None
elif inClinVarSet:
inputBuffer += line
def main():
parser = argparse.ArgumentParser()
parser.add_argument("clinVarXmlFilename")
args = parser.parse_args()
inputBuffer = ""
with gzip.open(args.clinVarXmlFilename) as inputFile:
inClinVarSet = False
for line in inputFile:
#print "inClinVarSet", inClinVarSet, " input:", line.rstrip()
if "<ClinVarSet" in line:
inHeader = False
inputBuffer = line
inClinVarSet = True
elif "</ClinVarSet>" in line:
inputBuffer += line
inClinVarSet = False
cvs = ET.fromstring(inputBuffer)
if clinvar.isCurrent(cvs):
submissionSet = clinvar.clinVarSet(cvs)
variant = submissionSet.referenceAssertion.variant
if variant != None:
if variant.geneSymbol == "BRCA1" or variant.geneSymbol == "BRCA2":
print inputBuffer
inputBuffer = None
elif inClinVarSet:
inputBuffer += line
else:
if len(line) > 1:
print line.rstrip()
def main():
parser = argparse.ArgumentParser()
parser.add_argument("clinVarXmlFilename")
args = parser.parse_args()
inputBuffer = ""
with gzip.open(args.clinVarXmlFilename) as inputFile:
inClinVarSet = False
for line in inputFile:
#print "inClinVarSet", inClinVarSet, " input:", line.rstrip()
if "<ClinVarSet" in line:
inHeader = False
inputBuffer = line
inClinVarSet = True
elif "</ClinVarSet>" in line:
inputBuffer += line
inClinVarSet = False
cvs = ET.fromstring(inputBuffer)
if clinvar.isCurrent(cvs):
submissionSet = clinvar.clinVarSet(cvs)
variant = submissionSet.referenceAssertion.variant
if variant != None:
if variant.geneSymbol == "BRCA1" or variant.geneSymbol == "BRCA2":
print inputBuffer
inputBuffer = None
elif inClinVarSet:
inputBuffer += line
else:
if len(line) > 1:
print line.rstrip()
def main():
parser = argparse.ArgumentParser()
parser.add_argument("clinVarXmlFilename")
parser.add_argument('-a', "--assembly", default="GRCh38")
args = parser.parse_args()
printHeader()
tree = ET.parse(args.clinVarXmlFilename)
root = tree.getroot()
for cvs in root.findall("ClinVarSet"):
if clinvar.isCurrent(cvs):
submissionSet = clinvar.clinVarSet(cvs)
ra = submissionSet.referenceAssertion
for oa in submissionSet.otherAssertions.values():
submitter = oa.submitter
if oa.method != "literature only" or oa.submitter == "Counsyl":
if oa.origin != "somatic" and oa.clinicalSignificance != "none provided" and oa.clinicalSignificance != "not provided":
variant = ra.variant
hgvs = re.sub("\(" + "(BRCA[1|2])" + "\)",
"", variant.name.split()[0])
proteinChange = None
if variant.attribute.has_key("HGVS, protein, RefSeq"):
proteinChange = variant.attribute["HGVS, protein, RefSeq"]
if not re.search("^NP", hgvs):
chrom = None
start = None
referenceAllele = None
alternateAllele = None
genomicCoordinate = "chrNone:None:None>None"
if args.assembly in variant.coordinates:
genomicData = variant.coordinates[args.assembly]
chrom = genomicData.chrom
start = genomicData.start
referenceAllele = genomicData.referenceAllele
alternateAllele = genomicData.alternateAllele
genomicCoordinate = "chr%s:%s:%s>%s" % (chrom,
start, referenceAllele,
alternateAllele)
print("\t".join((str(hgvs),
str(oa.submitter),
str(oa.clinicalSignificance),
str(oa.dateLastUpdated),
str(oa.accession),
str(oa.origin),
str(oa.method),
genomicCoordinate,
str(variant.geneSymbol),
str(proteinChange)
)))
def main():
parser = argparse.ArgumentParser()
parser.add_argument("clinVarXmlFilename")
args = parser.parse_args()
tree = ET.parse(args.clinVarXmlFilename)
root = tree.getroot()
newRoot = ET.Element(root.tag, attrib=root.attrib)
for cvs in root.findall("ClinVarSet"):
if clinvar.isCurrent(cvs):
submissionSet = clinvar.clinVarSet(cvs)
variant = submissionSet.referenceAssertion.variant
if variant != None:
if variant.geneSymbol == "BRCA1" or variant.geneSymbol == "BRCA2":
newRoot.append(cvs)
print(prettify(newRoot))
def main():
parser = argparse.ArgumentParser()
parser.add_argument("clinVarXmlFilename")
args = parser.parse_args()
tree = ET.parse(args.clinVarXmlFilename)
root = tree.getroot()
newRoot = ET.Element(root.tag, attrib=root.attrib)
for cvs in root.findall("ClinVarSet"):
if clinvar.isCurrent(cvs):
submissionSet = clinvar.clinVarSet(cvs)
variant = submissionSet.referenceAssertion.variant
if variant != None:
if variant.geneSymbol == "BRCA1" or variant.geneSymbol == "BRCA2":
newRoot.append(cvs)
print(prettify(newRoot))
def main():
parser = argparse.ArgumentParser()
parser.add_argument("clinVarXmlFilename")
parser.add_argument(
'-a',
"--artifacts_dir",
help='Artifacts directory with pipeline artifact files.')
args = parser.parse_args()
logging_level = logging.DEBUG
log_file_path = args.artifacts_dir + "clinvarbrcapy.log"
logging.basicConfig(filename=log_file_path,
filemode="w",
level=logging_level)
inputBuffer = ""
with gzip.open(args.clinVarXmlFilename) as inputFile:
inClinVarSet = False
for line in inputFile:
if "<ClinVarSet" in line:
inHeader = False
inputBuffer = line
inClinVarSet = True
elif "</ClinVarSet>" in line:
inputBuffer += line
inClinVarSet = False
cvs = ET.fromstring(inputBuffer)
if clinvar.isCurrent(cvs):
try:
submissionSet = clinvar.clinVarSet(cvs)
except AttributeError:
# TODO: this is a hack to avoid errors, figure out how to correctly handle these reports.
logging.debug(
"AttributeError running clinvar.clinVarSet(cvs), inputBuffer: %s, cvs: %s",
inputBuffer, cvs)
continue
variant = submissionSet.referenceAssertion.variant
if variant != None:
if variant.geneSymbol == "BRCA1" or variant.geneSymbol == "BRCA2":
print inputBuffer
inputBuffer = None
elif inClinVarSet:
inputBuffer += line
else:
if len(line) > 1:
print line.rstrip()
def main():
parser = argparse.ArgumentParser()
parser.add_argument("clinVarXmlFilename")
parser.add_argument('-a', "--assembly", default="GRCh38")
args = parser.parse_args()
printHeader()
tree = ET.parse(args.clinVarXmlFilename)
root = tree.getroot()
for cvs in root.findall("ClinVarSet"):
if clinvar.isCurrent(cvs):
submissionSet = clinvar.clinVarSet(cvs)
ra = submissionSet.referenceAssertion
for oa in submissionSet.otherAssertions.values():
submitter = oa.submitter
variant = ra.variant
hgvs = re.sub("\(" + "(BRCA[1|2])" + "\)", "",
variant.name.split()[0])
proteinChange = None
if variant.attribute.has_key("HGVS, protein, RefSeq"):
proteinChange = variant.attribute["HGVS, protein, RefSeq"]
chrom = None
start = None
referenceAllele = None
alternateAllele = None
if args.assembly in variant.coordinates:
genomicData = variant.coordinates[args.assembly]
chrom = genomicData.chrom
start = genomicData.start
referenceAllele = genomicData.referenceAllele
alternateAllele = genomicData.alternateAllele
genomicCoordinate = "chr%s:%s:%s>%s" % (
chrom, start, referenceAllele, alternateAllele)
print("\t".join(
(str(hgvs), oa.submitter.encode('utf-8'),
str(oa.clinicalSignificance), str(oa.dateLastUpdated),
str(oa.accession), str(oa.id), str(oa.origin),
str(oa.method), genomicCoordinate,
str(variant.geneSymbol), str(proteinChange))))